Pitch-Scaled Analysis based Residual Reconstruction for Speech Analysis and Synthesis

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 智能交互

	Pitch-Scaled Analysis based Residual Reconstruction for Speech Analysis and Synthesis
	Wen, Zhengqi; Kawahara, Hideki; Tao, Jianhua; Zhengqi Wen
	2012
会议日期	2012
会议地点	美国
关键词	Speech Parametric Representation Pitch-scaled Analysis Voicing Cut-off Frequency Principal Component Analysis
页码	374-377
英文摘要	The typical problem in LPC-like vocoder is buzzing sound which is mainly due to the simple pulse train or noise excitation model. One way to improve it is to reconstruct the residual obtained from inverse filtering. So a new parametric representation of speech based on pitch-scaled analysis is proposed in this paper. Pitch-scaled analysis is used to extract the periodic spectrum of residual with half pitch period length. Then these periodic spectrums are de-correlated by principal component analysis (PCA) to reduce their dimension. Aperiodic measure is defined as the harmonic-to-noise ratio in the frequency domain where voicing cut-off frequency (VCO) is used to control the smoothness of aperiodicity. Periodic spectrum and aperiodic measure together with F0 are indicated as excitation parameters in the proposed LPC vocoder. Experimental results show that this proposed vocoder can get a mean opinion score (MOS) of 4.1 for a female voice before dimensionality reduction and keep the high-quality property after parameter compression.
会议录	Annual Conference of the International Speech Communication Association (INTERSPEECH)
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/41278]
专题	模式识别国家重点实验室_智能交互
通讯作者	Zhengqi Wen
推荐引用方式 GB/T 7714	Wen, Zhengqi,Kawahara, Hideki,Tao, Jianhua,et al. Pitch-Scaled Analysis based Residual Reconstruction for Speech Analysis and Synthesis[C]. 见:. 美国. 2012.